© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48203
    Prev
    Next
    INDEX
    Explanations

    project

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on numerical tokens and measures—i.e. digit sequences and size/quantity figures in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    śni
    -0.79
    λους
    -0.75
    닷
    -0.75
    Handlung
    -0.75
    ܀
    -0.74
    tapeta
    -0.73
    负担
    -0.73
    attore
    -0.73
    umenten
    -0.73
    艏
    -0.72
    POSITIVE LOGITS
     project
    7.75
     projects
    6.34
    project
    5.16
     proyecto
    4.81
    项目
    4.81
     проекта
    4.56
    PROJECT
    4.44
    プロジェクト
    4.31
     پروژه
    4.25
     Project
    4.22
    Activations Density 0.197%

    No Known Activations